Research Topics in Spoken Dialogue Technology
Spoken dialogue technology is an exciting and active interdisciplinary research area, attracting researchers from disciplines such as computational linguistics, artificial intelligence, speech technology, linguistics and educational technology. This chapter presents a selection of current research issues in spoken dialogue technology beginning with Information State Theory, an influential approach to the representation of dialogue context that can play an important role in dialogue management for advanced dialogue systems. Following this the issue of error handling is discussed. This is an important issue in spoken dialogue technology, due to the pervasiveness of errors at all levels of analysis when interacting with a spoken dialogue system. The discussion will focus mainly on methods for error detection, including the use of machine learning techniques to predict the circumstances in which errors are likely to occur.
KeywordsSpeech Recognition Markov Decision Process Automatic Speech Recognition Dialogue System Dialogue Strategy
Unable to display preview. Download preview PDF.